Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 775 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.9483. Min Act: -0.1700

Data Index: 886371 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.9035. Min Act: -0.1700

Data Index: 457269 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.9041. Min Act: -0.1700

Data Index: 1390922 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8879. Min Act: -0.1700

Data Index: 1456326 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8673. Min Act: -0.1700

Data Index: 1437368 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8846. Min Act: -0.1700

Data Index: 316217 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8626. Min Act: -0.1700

Data Index: 478344 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8388. Min Act: -0.1700

Data Index: 1174114 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8309. Min Act: -0.1700

Data Index: 1650322 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8312. Min Act: -0.1700

Data Index: 1369957 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7893. Min Act: -0.1700

Data Index: 361513 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8035. Min Act: -0.1700

Data Index: 1389742 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7849. Min Act: -0.1700

Data Index: 1490776 (Python Code)

Max Activating Token Index: 509

Text #13

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.8050. Min Act: -0.1700

Data Index: 382159 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7886. Min Act: -0.1700

Data Index: 357001 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7893. Min Act: -0.1700

Data Index: 1522131 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7753. Min Act: -0.1700

Data Index: 1635462 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7660. Min Act: -0.1700

Data Index: 1050563 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7675. Min Act: -0.1700

Data Index: 1114147 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 2.9483. Min Range: -2.9483

Max Act: 2.7666. Min Act: -0.1700

Data Index: 971313 (C4 (Web Text))

Max Activating Token Index: 966